© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3905
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ä°s
    -0.23
    -generator
    -0.21
    createQuery
    -0.20
    SSERT
    -0.20
    ,eg
    -0.20
    缶
    -0.20
    ç¬ŀ
    -0.20
    Mbps
    -0.20
     ÑģеÑĢÑĮезн
    -0.20
    iquement
    -0.19
    POSITIVE LOGITS
    getLocale
    0.24
     blackColor
    0.23
    glich
    0.19
     Jury
    0.19
     whiteColor
    0.19
    /MIT
    0.19
     branches
    0.18
    eworld
    0.18
    ActivityIndicator
    0.18
     BinaryTree
    0.18
    Activations Density 0.000%

    No Known Activations